docs(providers): add Requesty provider page - #1425
Open
Thibaultjaigu wants to merge 1 commit into
Open
Thibaultjaigu wants to merge 1 commit into
Thibaultjaigu wants to merge 1 commit into
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds docs/providers/requesty.md for the new
requesty/route being added in BerriAI/litellm#32893. Requesty is an OpenAI compatible LLM router. The page follows the layout of the recent CLF AI Gateway and SCX.ai pages: an overview table with the route prefix and base URL, the two environment variables, SDK examples for non streaming, streaming, function calling, reasoning and prompt caching, a proxy config.yaml walkthrough with OpenAI SDK and curl tabs, an EU endpoint section showingREQUESTY_API_BASE,api_baseand config.yaml forhttps://router.eu.requesty.ai/v1, the supported OpenAI parameters, and the exception class.Everything described on the page was checked against the provider code in the companion PR. Reasoning params are only listed for models the LiteLLM model map flags as reasoning capable,
reasoning_effort="max"is documented as being sent asxhigh,extra_bodypassthrough is documented with themodelandmessagesexception, and the cache_control move into the last content block is described for the model families the transformation handles.The page also registers
providers/requestyin sidebars.js between Replicate and RunwayML, and addsREQUESTY_API_BASEandREQUESTY_API_KEYrows to the environment variables reference table in docs/proxy/config_settings.md, matching the surrounding row format.Why now: the
documentationjob on BerriAI/litellm#32893 fails with "Environment variables read under ./litellm but mentioned nowhere in the docs: ['REQUESTY_API_BASE', 'REQUESTY_API_KEY']". That check reads this repo, so it keeps failing on the code PR until this page is merged.Verified locally:
tests/documentation_tests/test_env_keys.pyfrom the code PR passes against this branch in a layout that mimics CI (litellm source plus this repo at docs/my-website).python3 scripts/check-docs.py docsreports no structural problems across all 800 files.node scripts/check-writing-style.json the changed files passes.node --check sidebars.jspasses. Every model id used in the examples (openai/gpt-4o-mini,anthropic/claude-sonnet-4-6,openai/gpt-5,claude-sonnet-4-6) was confirmed against the liveGET /v1/modelsandGET /v1/models/managedresponses. I did not runnpm run buildsince I do not have node_modules installed locally.Disclosure: I work at Requesty. Happy to adjust anything to match project conventions.